Shijie Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shijie Tang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Feng Li
College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China
2 shared publications - Suyi Li
Jilin University
2 shared publications - Fan Luo
College of Applied Technology, Jilin University, ChangChun, China
1 shared publication - Hongtao Wei
School of Mechanics and Safety Engineering, Zhengzhou University, Zhengzhou, CHINA
1 shared publication - Wenji Xiong
The First Hospital of Jilin University, Changchun, China
1 shared publication
Latest Publications
- 8 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-9
Heart Sounds Classification Based on Feature Fusion Using Lightweight Neural Networks
Heart sounds are an important basis for evaluating heart disease. In recent years, auxiliary diagnosis technology of cardiovascular disease based on the detection of heart sound signals has become a research hotspot. A lightweight automatic heart sound classification method is presented in this study. It only needs to perform simple preprocessing on the heart sound data, and a neural network model is constructed to automatically extract the time–frequency features of heart sound data: where the convolution module extracts the frequency-domain characteristics, the loop module extracts the time-domain characteristics, and the features are then fused in series and parallel. Finally, the classification and recognition of heart sounds are realized based on the fusion features. At the same time, methods, such as group convolution, global average pooling, and gated loop mechanisms, are used to reduce the parameters and training time of the neural network. The experimental data from the PhysioNet database are used for testing. The recognition accuracy of the series feature fusion heart sound classification model is 95.00%, and the model size is 0.6 MB. In addition, the parallel feature fusion heart sound classification model is 95.50%, and the model size is 1.36 MB. Therefore, the lightweight heart sound classification model designed in this study contains fewer parameters and higher recognition accuracy. This makes it suitable for deployment in embedded devices. It also has important research significance for the development of portable heart sound detection equipment.
- 8 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-9
Heart Sounds Classification Based on Feature Fusion Using Lightweight Neural Networks
Heart sounds are an important basis for evaluating heart disease. In recent years, auxiliary diagnosis technology of cardiovascular disease based on the detection of heart sound signals has become a research hotspot. A lightweight automatic heart sound classification method is presented in this study. It only needs to perform simple preprocessing on the heart sound data, and a neural network model is constructed to automatically extract the time–frequency features of heart sound data: where the convolution module extracts the frequency-domain characteristics, the loop module extracts the time-domain characteristics, and the features are then fused in series and parallel. Finally, the classification and recognition of heart sounds are realized based on the fusion features. At the same time, methods, such as group convolution, global average pooling, and gated loop mechanisms, are used to reduce the parameters and training time of the neural network. The experimental data from the PhysioNet database are used for testing. The recognition accuracy of the series feature fusion heart sound classification model is 95.00%, and the model size is 0.6 MB. In addition, the parallel feature fusion heart sound classification model is 95.50%, and the model size is 1.36 MB. Therefore, the lightweight heart sound classification model designed in this study contains fewer parameters and higher recognition accuracy. This makes it suitable for deployment in embedded devices. It also has important research significance for the development of portable heart sound detection equipment.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 298-302
Attention based Subregion Aggregation Graph Convolution Networks with Extended Neighborhood
Graph Convolution Network (GCN) is a powerful model for graph representation learning. But affected by limited scope of neighborhood and average aggregation. GCNs unable to capture the feature representations from distant nodes, and lose the structural correlation and attribute correlation between nodes. Mapping nodes to a latent-space and building extended neighborhood can improve the problem, in theory. But the irrelevant messages of latent-space neighborhood can adversely affect the performance, and the experiments of predecessors showed that the disadvantages of latent-space neighborhood outweigh the advantages. In this paper, we propose an attention based subregion aggregation graph convolution networks, termed AG-GCN, an efficient representation learning model for node classification to overcome the weaknesses. AG-GCN utilize graph embedding to map the nodes that have the same label with the target node to its neighborhood in the vector space to build extended neighborhood, so the long-range dependencies can be captured. What’s more, we overcome the adverse effects of irrelevant messages from extended neighborhood, and catch the structural correlation as well as attribute correlation by multi region attention mechanism. Our experimental results show that combining network geometry and attention computation yields a general improvement of accuracy on most range of open datasets of graphs.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 298-302
Attention based Subregion Aggregation Graph Convolution Networks with Extended Neighborhood
Graph Convolution Network (GCN) is a powerful model for graph representation learning. But affected by limited scope of neighborhood and average aggregation. GCNs unable to capture the feature representations from distant nodes, and lose the structural correlation and attribute correlation between nodes. Mapping nodes to a latent-space and building extended neighborhood can improve the problem, in theory. But the irrelevant messages of latent-space neighborhood can adversely affect the performance, and the experiments of predecessors showed that the disadvantages of latent-space neighborhood outweigh the advantages. In this paper, we propose an attention based subregion aggregation graph convolution networks, termed AG-GCN, an efficient representation learning model for node classification to overcome the weaknesses. AG-GCN utilize graph embedding to map the nodes that have the same label with the target node to its neighborhood in the vector space to build extended neighborhood, so the long-range dependencies can be captured. What’s more, we overcome the adverse effects of irrelevant messages from extended neighborhood, and catch the structural correlation as well as attribute correlation by multi region attention mechanism. Our experimental results show that combining network geometry and attention computation yields a general improvement of accuracy on most range of open datasets of graphs.
- Open Access
- 10 January 2020
- Published by Wiley in BioMed Research International
- Vol. 2020 (1) , 5846191
A Review of Computer‐Aided Heart Sound Detection Techniques
Cardiovascular diseases have become one of the most prevalent threats to human health throughout the world. As a noninvasive assistant diagnostic tool, the heart sound detection techniques play an important role in the prediction of cardiovascular diseases. In this paper, the latest development of the computer‐aided heart sound detection techniques over the last five years has been reviewed. There are mainly the following aspects: the theories of heart sounds and the relationship between heart sounds and cardiovascular diseases; the key technologies used in the processing and analysis of heart sound signals, including denoising, segmentation, feature extraction and classification; with emphasis, the applications of deep learning algorithm in heart sound processing. In the end, some areas for future research in computer‐aided heart sound detection techniques are explored, hoping to provide reference to the prediction of cardiovascular diseases.
- 10 January 2020
- Published by Wiley in BioMed Research International
- Vol. 2020 (1) , 5846191
Open AccessA Review of Computer‐Aided Heart Sound Detection Techniques
Cardiovascular diseases have become one of the most prevalent threats to human health throughout the world. As a noninvasive assistant diagnostic tool, the heart sound detection techniques play an important role in the prediction of cardiovascular diseases. In this paper, the latest development of the computer‐aided heart sound detection techniques over the last five years has been reviewed. There are mainly the following aspects: the theories of heart sounds and the relationship between heart sounds and cardiovascular diseases; the key technologies used in the processing and analysis of heart sound signals, including denoising, segmentation, feature extraction and classification; with emphasis, the applications of deep learning algorithm in heart sound processing. In the end, some areas for future research in computer‐aided heart sound detection techniques are explored, hoping to provide reference to the prediction of cardiovascular diseases.